Marown/yacy_search_server
1
0
Fork 0
mirror of https://github.com/yacy/yacy_search_server.git synced 2024-09-21 00:00:13 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity
2a9d868f6d
yacy_search_server/source/de/anomic/plasma/plasmaCrawlLURL.java
orbiter 2a9d868f6d - removed object cache from kelondroTree 
- generalized object caching and added new object caching class
- added object caching wherever kelondroTree was used
- added object caching also to usage of kelondroFlex
- added object buffering (a write cache) to NURLs
- added many assert statements; fixed bugs here and there
- added missing close methods to latest added classes

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@2858 6c8d7289-2bf4-0310-a012-ef5d649a1542
2006-10-24 13:48:16 +00:00

659 lines
30 KiB
Java
Raw Blame History

// plasmaCrawlLURL.java
// -----------------------
// part of YaCy
// (C) by Michael Peter Christen; mc@anomic.de
// first published on http://www.anomic.de
// Frankfurt, Germany, 2004
//
// $LastChangedDate$
// $LastChangedRevision$
// $LastChangedBy$
//
// This program is free software; you can redistribute it and/or modify
// it under the terms of the GNU General Public License as published by
// the Free Software Foundation; either version 2 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
//
// You should have received a copy of the GNU General Public License
// along with this program; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
//
// Using this software in any meaning (reading, learning, copying, compiling,
// running) means that you agree that the Author(s) is (are) not responsible
// for cost, loss of data or any harm that may be caused directly or indirectly
// by usage of this softare or this documentation. The usage of this software
// is on your own risk. The installation and usage (starting/running) of this
// software may allow other people or application to access your computer and
// any attached devices and is highly dependent on the configuration of the
// software which must be done by the user of the software; the author(s) is
// (are) also not responsible for proper configuration and usage of the
// software, even if provoked by documentation provided together with
// the software.
//
// Any changes to this file according to the GPL as documented in the file
// gpl.txt aside this file in the shipment you received can be done to the
// lines that follows this copyright notice here, but changes must not be
// done inside the copyright notive above. A re-distribution must contain
// the intact and unchanged copyright notice.
// Contributions and changes to the program code must be marked as such.
/*
This class provides storage functions for the plasma search engine.
- the url-specific properties, including condenser results
- the text content of the url
Both entities are accessed with a hash, which is based on the MD5
algorithm. The MD5 is not encoded as a hex value, but a b64 value.
*/
package de.anomic.plasma;
import java.io.File;
import java.io.IOException;
import java.net.MalformedURLException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.HashSet;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.Locale;
import de.anomic.http.httpc;
import de.anomic.http.httpc.response;
import de.anomic.index.indexEntry;
import de.anomic.index.indexURL;
import de.anomic.kelondro.kelondroBufferedIndex;
import de.anomic.kelondro.kelondroCachedIndex;
import de.anomic.kelondro.kelondroFlexSplitTable;
import de.anomic.kelondro.kelondroBase64Order;
import de.anomic.kelondro.kelondroRow;
import de.anomic.kelondro.kelondroTree;
import de.anomic.net.URL;
import de.anomic.plasma.urlPattern.plasmaURLPattern;
import de.anomic.server.serverCodings;
import de.anomic.server.serverObjects;
import de.anomic.server.logging.serverLog;
import de.anomic.tools.bitfield;
import de.anomic.tools.nxTools;
import de.anomic.yacy.yacyCore;
import de.anomic.yacy.yacySeed;
public final class plasmaCrawlLURL extends indexURL {
// result stacks;
// these have all entries of form
// strings: urlHash + initiatorHash + ExecutorHash
private final LinkedList externResultStack; // 1 - remote index: retrieved by other peer
private final LinkedList searchResultStack; // 2 - partly remote/local index: result of search queries
private final LinkedList transfResultStack; // 3 - partly remote/local index: result of index transfer
private final LinkedList proxyResultStack; // 4 - local index: result of proxy fetch/prefetch
private final LinkedList lcrawlResultStack; // 5 - local index: result of local crawling
private final LinkedList gcrawlResultStack; // 6 - local index: triggered external
private boolean newdb;
public plasmaCrawlLURL(File plasmaPath, File indexPath, int bufferkb, long preloadTime, boolean newdb) {
super();
this.newdb = newdb;
try {
if (newdb) {
urlIndexFile = new kelondroBufferedIndex(new kelondroCachedIndex(new kelondroFlexSplitTable(new File(indexPath, "PUBLIC/TEXT"), "urls", bufferkb / 2 * 0x400, preloadTime, plasmaCrawlLURLNewEntry.rowdef, kelondroBase64Order.enhancedCoder), bufferkb / 2 * 0x400));
} else {
File oldLURLDB = new File(plasmaPath, "urlHash.db");
oldLURLDB.getParentFile().mkdirs();
urlIndexFile = new kelondroBufferedIndex(new kelondroCachedIndex(new kelondroTree(oldLURLDB, bufferkb / 2 * 0x400, preloadTime, plasmaCrawlLURLOldEntry.rowdef), bufferkb / 2 * 0x400));
}
} catch (IOException e) {
e.printStackTrace();
System.exit(-1);
}
// init result stacks
externResultStack = new LinkedList();
searchResultStack = new LinkedList();
transfResultStack = new LinkedList();
proxyResultStack = new LinkedList();
lcrawlResultStack = new LinkedList();
gcrawlResultStack = new LinkedList();
}
public synchronized void stack(plasmaCrawlLURLEntry e, String initiatorHash, String executorHash, int stackType) {
if (e == null) { return; }
try {
if (initiatorHash == null) { initiatorHash = dummyHash; }
if (executorHash == null) { executorHash = dummyHash; }
switch (stackType) {
case 0: break;
case 1: externResultStack.add(e.hash() + initiatorHash + executorHash); break;
case 2: searchResultStack.add(e.hash() + initiatorHash + executorHash); break;
case 3: transfResultStack.add(e.hash() + initiatorHash + executorHash); break;
case 4: proxyResultStack.add(e.hash() + initiatorHash + executorHash); break;
case 5: lcrawlResultStack.add(e.hash() + initiatorHash + executorHash); break;
case 6: gcrawlResultStack.add(e.hash() + initiatorHash + executorHash); break;
}
return;
} catch (Exception ex) {
System.out.println("INTERNAL ERROR in newEntry/2: " + ex.toString());
return;
}
}
public synchronized void notifyGCrawl(String urlHash, String initiatorHash, String executorHash) {
gcrawlResultStack.add(urlHash + initiatorHash + executorHash);
}
public synchronized void flushCacheSome() {
try {
((kelondroBufferedIndex) urlIndexFile).flushSome();
} catch (IOException e) {}
}
public synchronized int writeCacheSize() {
return ((kelondroBufferedIndex) urlIndexFile).writeBufferSize();
}
public synchronized plasmaCrawlLURLEntry load(String urlHash, indexEntry searchedWord) {
// generates an plasmaLURLEntry using the url hash
// to speed up the access, the url-hashes are buffered
// in the hash cache.
// we have two options to find the url:
// - look into the hash cache
// - look into the filed properties
// if the url cannot be found, this returns null
try {
kelondroRow.Entry entry = urlIndexFile.get(urlHash.getBytes());
if (entry == null) return null;
if (newdb)
return new plasmaCrawlLURLNewEntry(entry, searchedWord);
else
return new plasmaCrawlLURLOldEntry(entry, searchedWord);
} catch (IOException e) {
return null;
}
}
public synchronized void store(plasmaCrawlLURLEntry entry) throws IOException {
// Check if there is a more recent Entry already in the DB
plasmaCrawlLURLEntry oldEntry;
try {
if (exists(entry.hash())) {
oldEntry = load(entry.hash(), null);
} else {
oldEntry = null;
}
} catch (Exception e) {
oldEntry = null;
}
if ((oldEntry != null) && (entry.isOlder(oldEntry))) {
// the fetched oldEntry is better, so return its properties instead of the new ones
// this.urlHash = oldEntry.urlHash; // unnecessary, should be the same
// this.url = oldEntry.url; // unnecessary, should be the same
entry = oldEntry;
return; // this did not need to be stored, but is updated
}
urlIndexFile.put(entry.toRowEntry(), entry.loaddate());
}
public synchronized plasmaCrawlLURLEntry newEntry(String propStr) {
if (propStr.startsWith("{") && propStr.endsWith("}")) {
if (newdb)
return new plasmaCrawlLURLNewEntry(serverCodings.s2p(propStr.substring(1, propStr.length() - 1)));
else
return new plasmaCrawlLURLOldEntry(serverCodings.s2p(propStr.substring(1, propStr.length() - 1)));
} else {
return null;
}
}
public synchronized plasmaCrawlLURLEntry newEntry(
URL url,
String descr,
String author,
String tags,
String ETag,
Date mod,
Date load,
Date fresh,
String referrer,
byte[] md5,
long size,
int wc,
char dt,
bitfield flags,
String lang,
int llocal,
int lother,
int laudio,
int limage,
int lvideo,
int lapp) {
if (newdb)
return new plasmaCrawlLURLNewEntry(url, descr, author, tags, ETag, mod, load, fresh, referrer, md5,
size, wc, dt, flags, lang, llocal, lother, laudio, limage, lvideo, lapp);
else
return new plasmaCrawlLURLOldEntry(url, descr, author, tags, ETag, mod, load, fresh, referrer, md5,
size, wc, dt, flags, lang, llocal, lother, laudio, limage, lvideo, lapp);
}
public synchronized int getStackSize(int stack) {
switch (stack) {
case 1: return externResultStack.size();
case 2: return searchResultStack.size();
case 3: return transfResultStack.size();
case 4: return proxyResultStack.size();
case 5: return lcrawlResultStack.size();
case 6: return gcrawlResultStack.size();
}
return -1;
}
public synchronized String getUrlHash(int stack, int pos) {
switch (stack) {
case 1: return ((String) externResultStack.get(pos)).substring(0, urlHashLength);
case 2: return ((String) searchResultStack.get(pos)).substring(0, urlHashLength);
case 3: return ((String) transfResultStack.get(pos)).substring(0, urlHashLength);
case 4: return ((String) proxyResultStack.get(pos)).substring(0, urlHashLength);
case 5: return ((String) lcrawlResultStack.get(pos)).substring(0, urlHashLength);
case 6: return ((String) gcrawlResultStack.get(pos)).substring(0, urlHashLength);
}
return null;
}
public synchronized String getInitiatorHash(int stack, int pos) {
switch (stack) {
case 1: return ((String) externResultStack.get(pos)).substring(urlHashLength, urlHashLength * 2);
case 2: return ((String) searchResultStack.get(pos)).substring(urlHashLength, urlHashLength * 2);
case 3: return ((String) transfResultStack.get(pos)).substring(urlHashLength, urlHashLength * 2);
case 4: return ((String) proxyResultStack.get(pos)).substring(urlHashLength, urlHashLength * 2);
case 5: return ((String) lcrawlResultStack.get(pos)).substring(urlHashLength, urlHashLength * 2);
case 6: return ((String) gcrawlResultStack.get(pos)).substring(urlHashLength, urlHashLength * 2);
}
return null;
}
public synchronized String getExecutorHash(int stack, int pos) {
switch (stack) {
case 1: return ((String) externResultStack.get(pos)).substring(urlHashLength * 2, urlHashLength * 3);
case 2: return ((String) searchResultStack.get(pos)).substring(urlHashLength * 2, urlHashLength * 3);
case 3: return ((String) transfResultStack.get(pos)).substring(urlHashLength * 2, urlHashLength * 3);
case 4: return ((String) proxyResultStack.get(pos)).substring(urlHashLength * 2, urlHashLength * 3);
case 5: return ((String) lcrawlResultStack.get(pos)).substring(urlHashLength * 2, urlHashLength * 3);
case 6: return ((String) gcrawlResultStack.get(pos)).substring(urlHashLength * 2, urlHashLength * 3);
}
return null;
}
public synchronized boolean removeStack(int stack, int pos) {
Object prevElement = null;
switch (stack) {
case 1: prevElement = externResultStack.remove(pos); break;
case 2: prevElement = searchResultStack.remove(pos); break;
case 3: prevElement = transfResultStack.remove(pos); break;
case 4: prevElement = proxyResultStack.remove(pos); break;
case 5: prevElement = lcrawlResultStack.remove(pos); break;
case 6: prevElement = gcrawlResultStack.remove(pos); break;
}
return prevElement != null;
}
public synchronized void clearStack(int stack) {
switch (stack) {
case 1: externResultStack.clear(); break;
case 2: searchResultStack.clear(); break;
case 3: transfResultStack.clear(); break;
case 4: proxyResultStack.clear(); break;
case 5: lcrawlResultStack.clear(); break;
case 6: gcrawlResultStack.clear(); break;
}
}
public synchronized boolean remove(String urlHash) {
if (urlHash == null) return false;
try {
kelondroRow.Entry r = urlIndexFile.remove(urlHash.getBytes());
if (r == null) return false;
for (int stack = 1; stack <= 6; stack++) {
for (int i = getStackSize(stack) - 1; i >= 0; i--) {
if (getUrlHash(stack, i).equals(urlHash)) {
removeStack(stack, i);
return true;
}
}
}
return true;
} catch (IOException e) {
return false;
}
}
public synchronized boolean exists(String urlHash) {
try {
return (urlIndexFile.get(urlHash.getBytes()) != null);
} catch (IOException e) {
return false;
}
}
private static SimpleDateFormat dayFormatter = new SimpleDateFormat("yyyy/MM/dd", Locale.US);
private static String daydate(Date date) {
if (date == null) {
return "";
} else {
return dayFormatter.format(date);
}
}
public serverObjects genTableProps(int tabletype, int lines, boolean showInit, boolean showExec, String dfltInit, String dfltExec, String feedbackpage, boolean makeLink) {
/* serverLog.logFinest("PLASMA", "plasmaCrawlLURL/genTableProps tabletype=" + tabletype + " lines=" + lines +
" showInit=" + showInit + " showExec=" + showExec +
" dfltInit=" + dfltInit + " dfltExec=" + dfltExec +
" feedbackpage=" + feedbackpage + " makeLink=" + makeLink); */
final serverObjects prop = new serverObjects();
if (getStackSize(tabletype) == 0) {
prop.put("table", 0);
return prop;
}
prop.put("table", 1);
if (lines > getStackSize(tabletype)) lines = getStackSize(tabletype);
if (lines == getStackSize(tabletype)) {
prop.put("table_size", 0);
} else {
prop.put("table_size", 1);
prop.put("table_size_count", lines);
}
prop.put("table_size_all", getStackSize(tabletype));
prop.put("table_feedbackpage", feedbackpage);
prop.put("table_tabletype", tabletype);
prop.put("table_showInit", (showInit) ? 1 : 0);
prop.put("table_showExec", (showExec) ? 1 : 0);
boolean dark = true;
String urlHash, initiatorHash, executorHash;
String cachepath, urlstr, urltxt;
yacySeed initiatorSeed, executorSeed;
plasmaCrawlLURLEntry urle;
// needed for getCachePath(url)
final plasmaSwitchboard switchboard = plasmaSwitchboard.getSwitchboard();
final plasmaHTCache cacheManager = switchboard.getCacheManager();
int i, cnt = 0;
for (i = getStackSize(tabletype) - 1; i >= (getStackSize(tabletype) - lines); i--) {
initiatorHash = getInitiatorHash(tabletype, i);
executorHash = getExecutorHash(tabletype, i);
// serverLog.logFinest("PLASMA", "plasmaCrawlLURL/genTableProps initiatorHash=" + initiatorHash + " executorHash=" + executorHash);
urlHash = getUrlHash(tabletype, i);
// serverLog.logFinest("PLASMA", "plasmaCrawlLURL/genTableProps urlHash=" + urlHash);
try {
urle = load(urlHash, null);
plasmaCrawlLURLEntry.Components comp = urle.comp();
// serverLog.logFinest("PLASMA", "plasmaCrawlLURL/genTableProps urle=" + urle.toString());
initiatorSeed = yacyCore.seedDB.getConnected(initiatorHash);
executorSeed = yacyCore.seedDB.getConnected(executorHash);
urlstr = comp.url().toNormalform();
urltxt = nxTools.shortenURLString(urlstr, 72); // shorten the string text like a URL
cachepath = cacheManager.getCachePath(new URL(urlstr)).toString().replace('\\', '/').substring(cacheManager.cachePath.toString().length() + 1);
prop.put("table_indexed_" + cnt + "_dark", (dark) ? 1 : 0);
prop.put("table_indexed_" + cnt + "_feedbackpage", feedbackpage);
prop.put("table_indexed_" + cnt + "_tabletype", tabletype);
prop.put("table_indexed_" + cnt + "_urlhash", urlHash);
prop.put("table_indexed_" + cnt + "_showInit", (showInit) ? 1 : 0);
prop.put("table_indexed_" + cnt + "_showInit_initiatorSeed", (initiatorSeed == null) ? dfltInit : initiatorSeed.getName());
prop.put("table_indexed_" + cnt + "_showExec", (showExec) ? 1 : 0);
prop.put("table_indexed_" + cnt + "_showExec_executorSeed", (executorSeed == null) ? dfltExec : executorSeed.getName());
prop.put("table_indexed_" + cnt + "_moddate", daydate(urle.moddate()));
prop.put("table_indexed_" + cnt + "_wordcount", urle.wordCount());
prop.put("table_indexed_" + cnt + "_urldescr", comp.descr());
prop.put("table_indexed_" + cnt + "_url", (cachepath == null) ? "-not-cached-" : ((makeLink) ? ("<a href=\"CacheAdmin_p.html?action=info&path=" + cachepath + "\" class=\"small\" title=\"" + urlstr + "\">" + urltxt + "</a>") : urlstr));
dark = !dark;
cnt++;
} catch (Exception e) {
serverLog.logSevere("PLASMA", "genTableProps", e);
}
}
prop.put("table_indexed", cnt);
return prop;
}
public class kiter implements Iterator {
// enumerates entry elements
Iterator i;
boolean error = false;
public kiter(boolean up, boolean rotating, String firstHash) throws IOException {
i = urlIndexFile.rows(up, rotating, (firstHash == null) ? null : firstHash.getBytes());
error = false;
}
public boolean hasNext() {
if (error) return false;
return i.hasNext();
}
public Object next() throws RuntimeException {
kelondroRow.Entry e = (kelondroRow.Entry) i.next();
if (e == null) return null;
try {
if (newdb)
return new plasmaCrawlLURLNewEntry(e, null);
else
return new plasmaCrawlLURLOldEntry(e, null);
} catch (IOException ex) {
throw new RuntimeException("error '" + ex.getMessage() + "' for hash " + e.getColString(0, null));
}
}
public void remove() {
i.remove();
}
}
public Iterator entries(boolean up, boolean rotating, String firstHash) throws IOException {
// enumerates entry elements
return new kiter(up, rotating, firstHash);
}
/**
* Uses an Iteration over urlHash.db to detect malformed URL-Entries.
* Damaged URL-Entries will be marked in a HashSet and removed at the end of the function.
*
* @param homePath Root-Path where all information is to be found.
*/
public void urldbcleanup() {
serverLog log = new serverLog("URLDBCLEANUP");
HashSet damagedURLS = new HashSet();
try {
Iterator eiter = entries(true, false, null);
int iteratorCount = 0;
while (eiter.hasNext()) try {
eiter.next();
iteratorCount++;
} catch (RuntimeException e) {
if(e.getMessage() != null) {
String m = e.getMessage();
damagedURLS.add(m.substring(m.length() - 12));
} else {
log.logSevere("RuntimeException:", e);
}
}
try { Thread.sleep(1000); } catch (InterruptedException e) { }
log.logInfo("URLs vorher: " + size() + " Entries loaded during Iteratorloop: " + iteratorCount + " kaputte URLs: " + damagedURLS.size());
Iterator eiter2 = damagedURLS.iterator();
String urlHash;
while (eiter2.hasNext()) {
urlHash = (String) eiter2.next();
// trying to fix the invalid URL
httpc theHttpc = null;
String oldUrlStr = null;
try {
// getting the url data as byte array
kelondroRow.Entry entry = urlIndexFile.get(urlHash.getBytes());
// getting the wrong url string
oldUrlStr = entry.getColString(1, null).trim();
int pos = -1;
if ((pos = oldUrlStr.indexOf("://")) != -1) {
// trying to correct the url
String newUrlStr = "http://" + oldUrlStr.substring(pos + 3);
URL newUrl = new URL(newUrlStr);
// doing a http head request to test if the url is correct
theHttpc = httpc.getInstance(newUrl.getHost(), newUrl.getHost(), newUrl.getPort(), 30000, false);
response res = theHttpc.HEAD(newUrl.getPath(), null);
if (res.statusCode == 200) {
entry.setCol(1, newUrl.toString().getBytes());
urlIndexFile.put(entry);
log.logInfo("UrlDB-Entry with urlHash '" + urlHash + "' corrected\n\tURL: " + oldUrlStr + " -> " + newUrlStr);
} else {
remove(urlHash);
log.logInfo("UrlDB-Entry with urlHash '" + urlHash + "' removed\n\tURL: " + oldUrlStr + "\n\tConnection Status: " + res.status);
}
}
} catch (Exception e) {
remove(urlHash);
log.logInfo("UrlDB-Entry with urlHash '" + urlHash + "' removed\n\tURL: " + oldUrlStr + "\n\tExecption: " + e.getMessage());
} finally {
if (theHttpc != null) try {
theHttpc.close();
httpc.returnInstance(theHttpc);
} catch (Exception e) { }
}
}
log.logInfo("URLs nachher: " + size() + " kaputte URLs: " + damagedURLS.size());
} catch (IOException e) {
log.logSevere("IOException", e);
}
}
// The Cleaner class was provided as "UrldbCleaner" by Hydrox
// see http://www.yacy-forum.de/viewtopic.php?p=18093#18093
public Cleaner makeCleaner() {
return new Cleaner();
}
public class Cleaner extends Thread {
private boolean run = true;
private boolean pause = false;
public int blacklistedUrls = 0;
public int totalSearchedUrls = 1;
public String lastBlacklistedUrl = "";
public String lastBlacklistedHash = "";
public String lastUrl = "";
public String lastHash = "";
public Cleaner() {
}
public void run() {
try {
serverLog.logInfo("URLDBCLEANER", "UrldbCleaner-Thread startet");
Iterator eiter = entries(true, false, null);
while (eiter.hasNext() && run) {
synchronized(this) {
if (this.pause) {
try {
this.wait();
} catch (InterruptedException e) {
serverLog.logWarning("URLDBCLEANER", "InterruptedException", e);
this.run = false;
return;
}
}
}
plasmaCrawlLURLEntry entry = (plasmaCrawlLURLEntry) eiter.next();
plasmaCrawlLURLEntry.Components comp = entry.comp();
totalSearchedUrls++;
if (plasmaSwitchboard.urlBlacklist.isListed(plasmaURLPattern.BLACKLIST_CRAWLER, comp.url()) ||
plasmaSwitchboard.urlBlacklist.isListed(plasmaURLPattern.BLACKLIST_DHT, comp.url())) {
lastBlacklistedUrl = comp.url().toNormalform();
lastBlacklistedHash = entry.hash();
serverLog.logFine("URLDBCLEANER", ++blacklistedUrls + " blacklisted (" + ((double)blacklistedUrls/totalSearchedUrls)*100 + "%): " + entry.hash() + " " + comp.url().toNormalform());
remove(entry.hash());
if (blacklistedUrls % 100 == 0) {
serverLog.logInfo("URLDBCLEANER", "Deleted " + blacklistedUrls + " URLs until now. Last deleted URL-Hash: " + lastBlacklistedUrl);
}
}
lastUrl = comp.url().toNormalform();
lastHash = entry.hash();
}
} catch (RuntimeException e) {
if (e.getMessage() != null && e.getMessage().indexOf("not found in LURL") != -1) {
serverLog.logWarning("URLDBCLEANER", "urlHash not found in LURL", e);
}
else {
serverLog.logWarning("URLDBCLEANER", "RuntimeException", e);
run = false;
}
} catch (IOException e) {
e.printStackTrace();
run = false;
}
serverLog.logInfo("URLDBCLEANER", "UrldbCleaner-Thread stopped");
}
public void abort() {
synchronized(this) {
run = false;
this.notifyAll();
}
}
public void pause() {
synchronized(this) {
if (!pause) {
pause = true;
serverLog.logInfo("URLDBCLEANER", "UrldbCleaner-Thread paused");
}
}
}
public void endPause() {
synchronized(this) {
if (pause) {
pause = false;
this.notifyAll();
serverLog.logInfo("URLDBCLEANER", "UrldbCleaner-Thread resumed");
}
}
}
}
public static void main(String[] args) {
// test-generation of url hashes for debugging
// one argument requires, will be treated as url
// returns url-hash
if (args[0].equals("-h")) try {
// arg 1 is url
System.out.println("HASH: " + urlHash(new URL(args[1])));
} catch (MalformedURLException e) {}
if (args[0].equals("-l")) try {
// arg 1 is path to URLCache
final plasmaCrawlLURL urls = new plasmaCrawlLURL(new File(args[1]), new File(args[2]), 1, 0, false);
final Iterator enu = urls.entries(true, false, null);
while (enu.hasNext()) {
System.out.println(((plasmaCrawlLURLEntry) enu.next()).toString());
}
} catch (Exception e) {
e.printStackTrace();
}
}
}
Reference in New Issue View Git Blame Copy Permalink